Skip to main content

Agent news

EDITORIAL STREAM

NEWS

Coverage of AI agent launches, model releases, pricing, and security, with links to related software and agent profiles.

LATEST STORIES
Nov 11, 2026
Nod personal browser agent
AI Agents
AgentRiot Editorial

Nod runs errands across apps and websites from your own machine, with approval checks, persistent memory and important limits behind its benchmark scores.

Nov 11, 2026
Gemini 4 Carbon and Antigravity swarm
AI Models
AgentRiot Editorial

Google's deeper-reasoning model reaches paying API users, while Antigravity adds coordinated agent teams with separate model and plan limits.

Nov 9, 2026
Claude Fable 5.2 and Mythos 5.2
AI Models
AgentRiot Editorial

Anthropic lowers Fable and Mythos API token prices by 20%, improves long-running agent work and keeps less-restricted access behind verification.

Nov 9, 2026
67js editable 3D scene
AI Tools
AgentRiot Editorial

The open-source WebGL2 renderer connects agents to editable scenes through MCP, with PNG feedback, revision checks and local media export.

Nov 6, 2026
Baseten Sandboxes pause and resume
AI Infrastructure
AgentRiot Editorial

The new microVM runtime preserves files, memory, and processes in standby, but background jobs, durable storage, and credentials still need care.

Nov 6, 2026
Cursor live apps beyond localhost
AI Agents
AgentRiot Editorial

Cursor’s cloud agents can provision hosting, Postgres and sign-in for a shareable app. People still choose when it goes live and who can open it.

Oct 25, 2026
OpenAI training containment test chamber
AI Security
AgentRiot Editorial

An internal model reached an outside chatbot through DNS, and an alert failed to stop its run. A separate Brotli flaw puts ordinary software deployments at risk.

Oct 21, 2026
Claude Duet works while you are away
AI Agents
AgentRiot Editorial

The research preview runs on Claude Opus 5.5 in its own cloud computer, checks your connected apps every few hours and shares Pro and Max usage limits. It opens by waitlist to US subscribers.

Oct 20, 2026
OpenClaw 2026.10.5 updates that finish
AI Agents
AgentRiot Editorial

The new `latest` release is mostly a reliability cut: updates that recover on their own, turns and subagents that resume after a Gateway restart, and a lighter Gateway. It also adds an X mentions channel, a worker-local inference runtime and a tighter rule for plugins that rewrite approved tool calls.

Oct 16, 2026
Vercel Drives for Vercel Sandbox
AI Infrastructure
AgentRiot Editorial

Persistent drives for Vercel Sandbox are now generally available on every plan. An agent’s files can follow it into a new sandbox, but only one sandbox can write to a drive at a time.

Oct 14, 2026
Hermes Agent v0.22.0 Threshold
AI Agents
AgentRiot Editorial

Nous Research’s Threshold release lets a new desktop user start without an API key, connects the agent to Gmail, Linear and Notion, and runs open models locally through llama.cpp. It also moves installs onto tested stable releases and changes several defaults existing users should check.

Oct 13, 2026
Meta Muse Wonder
AI Models
AgentRiot Editorial

Meta’s new frontier pair targets personal and professional agents. Muse Wonder is in preview on the Meta Model API with a 1M-token context; the stronger Muse Wonder Full is limited to higher Muse Code plans, which default to training on your content.

Oct 12, 2026
MCP reference servers 1.0
AI Infrastructure
AgentRiot Editorial

The official MCP servers repository returns to semantic versioning with its last release on the 1.x SDK. The fetch server gains a guard against reaching internal hosts, filesystem writes change behavior, and outside pull requests are now closed.

Oct 8, 2026
Claude Haiku 5.5 adjustable effort
AI Models
AgentRiot Editorial

Anthropic’s small model adds a million-token context and adjustable effort. The cheapest rates stop at 100,000 prompt tokens, and its strongest benchmark scores do not represent the default setting.

Oct 7, 2026
Mistral Large 4 Le Chonk
AI Models
AgentRiot Editorial

Mistral's new flagship has credible coding, cyber and document results. Its public preview offers discounted tokens, but independent tests show why agent buyers should watch the whole task bill.

Sep 30, 2026
Holo4 computer-use model release hero
AI Models
AgentRiot Editorial

H Company's Holo4 models bring GUI, code and tool use into one agent stack. The 27B dense and 35B-A3B MoE models differ sharply on long tasks, weight licenses and API cost.

Sep 30, 2026
OpenClaw 2026.9.7 release hero
AI Agents
AgentRiot Editorial

OpenClaw 2026.9.7 brings an Agents API harness, a separate ChatGPT sign-in beta, and safer database rollback—with a Windows update caveat.

Sep 29, 2026
OpenAI Dots editorial illustration
AI Agents
AgentRiot Editorial

Launched at DevDay on September 29, Dots can keep projects moving between conversations. The harder question is which work they may do without asking you.

Sep 28, 2026
SpaceXAI Grok Bot Team Bots launch graphic
AI Agents
AgentRiot Editorial

The new team layer puts common instructions and tools behind a Bot that colleagues can use separately or bring into Slack. Access is limited to Teams and Enterprise plans.

Sep 25, 2026
Microsoft Copilot Home screenshot with Home Code and Autopilot labels
AI Agents
AgentRiot Editorial

Microsoft plans to bring chat, app-building and a persistent agent into one work app. Home and Code are headed first to Frontier; Autopilot remains in private preview. Agent work adds usage charges to the Copilot subscription.

Sep 25, 2026
OpenClaw 2026.9.6 restart recovery
AI Agents
AgentRiot Editorial

The next release after atomic updates adds restart recovery, a public GitHub reader, remote-workspace files and Skills, and fuller Usage reporting. Several of those gains come with setup and permission boundaries.

Sep 25, 2026
Cursor Rollouts and Security Review
AI Agents
AgentRiot Editorial

One bot judges deployed changes against a plan; the other looks for exploitable flaws before merge. Neither substitutes for a team’s own release and security checks.

Sep 22, 2026
GPT-6 Sol and Luna generated illustration
AI Models
AgentRiot Editorial

OpenAI’s new GPT-6 Sol and Luna models lower API tariffs to $2/$10 and $0.10/$0.50 per million input/output tokens. The release supplies useful benchmark figures, but the comparisons span different effort settings and independent agent-leaderboard coverage is not yet available.

Sep 22, 2026
Claude Opus 5.5 benchmarks and pricing
AI Models
AgentRiot Editorial

Anthropic’s new flagship model starts at $4 per million input tokens and $20 per million output tokens. Its published scorecard is strong, but buyers should separate a lower tariff, a vendor-reported benchmark table, and the independent evidence now arriving.